Zero-inflated negative binomial mixed model: an application to two microbial organisms important in oesophagitis

Epidemiology and Infection - Tập 144 Số 11 - Trang 2447-2455 - 2016
Rui Fang1, Brandie D. Wagner1,2,3, J. Kirk Harris2,3, Sophie Fillon4
1Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado Denver, Aurora, CO, USA
2Department of Pediatrics, Division of Pulmonology, University of Colorado Denver, School of Medicine, Aurora, CO, USA
3University of Colorado Microbiome Research Consortium (MiRC), Aurora, CO, USA
4Department of Pediatrics, Section of Gastroenterology, Hepatology and Nutrition, Digestive Health Institute, Gastrointestinal Eosinophilic Diseases Program, Mucosal Inflammation Program, Children's Hospital Colorado, University of Colorado Denver, School of Medicine, Aurora, CO, USA

Tóm tắt

SUMMARYAltered microbial communities are thought to play an important role in eosinophilic oesophagitis, an allergic inflammatory condition of the oesophagus. Identification of the majority of organisms present in human-associated microbial communities is feasible with the advent of high throughput sequencing technology. However, these data consist of non-negative, highly skewed sequence counts with a large proportion of zeros. In addition, hierarchical study designs are often performed with repeated measurements or multiple samples collected from the same subject, thus requiring approaches to account for within-subject variation, yet only a small number of microbiota studies have applied hierarchical regression models. In this paper, we describe and illustrate the use of a hierarchical regression-based approach to evaluate multiple factors for a small number of organisms individually. More specifically, the zero-inflated negative binomial mixed model with random effects in both the count and zero-inflated parts is applied to evaluate associations with disease state while adjusting for potential confounders for two organisms of interest from a study of human microbiota sequence data in oesophagitis.

Từ khóa


Tài liệu tham khảo

10.1186/1471-2105-14-79

Greene W . Accounting for excess zeros and sample selection in Poisson and negative binomial regression models. Working paper. Department of Economics, Stern School of Business, New York University, 1994.

10.1101/gr.096651.109

10.1080/02664760802273203

10.1023/A:1021594923546

10.1371/journal.pone.0128346

10.1186/1471-2105-11-422

10.1186/2049-2618-2-4

10.1186/gb-2010-11-10-r106

10.1186/1471-2105-11-94

10.1186/s40168-015-0085-6

10.1126/science.1124234

10.1002/sim.860

10.1373/clinchem.2012.187617

10.1086/367657

10.1093/bioinformatics/btp616

10.1002/bimj.200390024

10.1038/nmeth.2658

10.1371/journal.pcbi.1003531

10.1038/nrmicro2974

Smith, 2012, The cervical microbiome over 7 years and a comparison of methodologies for its characterization, PLoS ONE, 7

10.1371/journal.pone.0042938

Thông tin
Thông tin xuất bản

Epidemiology and Infection

Tập 144 Số 11

2447-2455

Thông tin tác giả